Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5005 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.6097. Min Act: -0.1700
Data Index: 5843367 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5775. Min Act: -0.1700
Data Index: 6525465 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5614. Min Act: -0.1700
Data Index: 3494223 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5291. Min Act: -0.1700
Data Index: 6667757 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5291. Min Act: -0.1700
Data Index: 2877546 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5129. Min Act: -0.1700
Data Index: 2478794 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5129. Min Act: -0.1700
Data Index: 7673460 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4967. Min Act: -0.1700
Data Index: 449075 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1919485 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4967. Min Act: -0.1700
Data Index: 6987894 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.5129. Min Act: -0.1700
Data Index: 7048089 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4967. Min Act: -0.1700
Data Index: 6553752 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4967. Min Act: -0.1700
Data Index: 1833744 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4967. Min Act: -0.1700
Data Index: 7794670 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4643. Min Act: -0.1700
Data Index: 4244863 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4805. Min Act: -0.1700
Data Index: 444868 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4805. Min Act: -0.1700
Data Index: 587773 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4805. Min Act: -0.1700
Data Index: 3265944 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4643. Min Act: -0.1700
Data Index: 6031309 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6097. Min Range: -2.6097
Max Act: 2.4643. Min Act: -0.1700
Data Index: 3489949 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19